domain: large-language-models
3756 products, primary matches first, then adoption-weighted; health v2 shown.
| Product | Health v2 | Stars | Maturity |
|---|---|---|---|
| google/tunix Tunix is a lightweight JAX-based library for post-training large language models, supporting supervised fine-tuning, preference optimizatio… | 83 | 2415 | active |
| jackmpcollins/magentic A Python library for seamlessly integrating LLMs into Python code via @prompt and @chatprompt decorators that return typed, structured outp… | 74 | 2415 | active |
| wan-h/awesome-digital-human-live2d An open-source digital human application that combines Live2D avatars with LLM-powered conversation, integrating ASR, LLM, TTS, and agent o… | 62 | 2413 | active |
| Jittor/JittorLLMs JittorLLMs is a large language model inference library built on the Jittor deep learning framework, supporting models like ChatGLM, LLaMA/L… | 34 | 2413 | active |
| X-PLUG/mPLUG-DocOwl mPLUG-DocOwl is a family of multimodal large language models from Alibaba for OCR-free document understanding, including DocOwl1.5 and DocO… | 39 | 2411 | active |
| lmnr-ai/index Index is an open-source browser agent that autonomously performs complex tasks on the web by turning any website into an accessible API. It… | 10 | 2411 | active |
| AI-Hypercomputer/maxtext MaxText is a high-performance, scalable open-source LLM training library written in pure Python/JAX, targeting Google Cloud TPUs and GPUs. … | 97 | 2408 | active |
| glidea/banana-prompt-quicker A Chrome extension that lets users quickly insert curated and custom prompts into Google AI Studio, Gemini, and any website input box via r… | 61 | 2405 | active |
| BloopAI/bloop bloop is a fast code search engine and desktop app that lets developers search their codebase with natural language, regex, and symbol quer… | 10 | 9499 | maintenance |
| sdi2200262/agentic-project-management APM (Agentic Project Management) is an open-source JavaScript framework and CLI for managing complex software projects with AI coding assis… | 76 | 2397 | active |
| The-Vibe-Company/companion Companion is an open-source tool for launching and managing fleets of task-optimized AI agents (built around Claude Code and Codex), with a… | 68 | 2396 | active |
| Nano-Collective/nanocoder Nanocoder is an open-source, terminal-based AI coding agent built by a community collective. It runs agentic coding workflows against any m… | 81 | 2384 | active |
| microsoft/Olive Olive is Microsoft's AI model optimization toolkit for the ONNX Runtime, automating finetuning, conversion, quantization, and compression o… | 91 | 2382 | active |
| BigDawnGhost/wenyi Wenyi is a Python CLI tool that translates EPUB books into Chinese using LLMs, with whole-book context analysis, real-time glossary extract… | 80 | 2381 | active |
| sdyckjq-lab/llm-wiki-skill A personal knowledge base Skill based on Andrej Karpathy's llm-wiki methodology, installable into AI CLI agents like Claude Code, Codex, Op… | 57 | 2378 | active |
| gkamradt/needle-in-a-haystack A benchmarking tool (niah / needlehaystack) that pressure-tests LLM long-context retrieval by sweeping context length x needle depth cells … | 72 | 2375 | active |
| RAIT-09/obsidian-agent-client An Obsidian plugin that brings AI coding agents like Claude Code, Codex, and Gemini CLI into the vault via the Agent Client Protocol (ACP).… | 83 | 2374 | active |
| FMInference/FlexLLMGen FlexLLMGen is a high-throughput generation engine for running large language models on a single GPU with limited memory. It uses IO-efficie… | 10 | 9352 | maintenance |
| apple/axlearn AXLearn is a Python deep learning library built on JAX and XLA for developing and training large-scale models, with an object-oriented conf… | 71 | 2372 | active |
| spacedriveapp/spacebot Spacebot is an opinionated AI agent harness written in Rust for teams, communities, and multi-user environments, deployable as a single sel… | 76 | 2371 | active |
| knowsuchagency/mcp2cli mcp2cli is a Python CLI tool that turns any MCP server, OpenAPI spec, or GraphQL endpoint into a command-line interface at runtime with zer… | 59 | 2370 | active |
| showlab/Paper2Video Paper2Video is a Python pipeline that automatically generates academic presentation videos from scientific papers, taking a paper PDF, a sp… | 48 | 2368 | active |
| she-llac/claude-counter A minimal browser extension (and userscript) that overlays token counts, cache countdown timers, and session/weekly usage bars on claude.ai… | 56 | 2366 | active |
| orhanerday/open-ai A community-maintained PHP SDK for accessing the OpenAI API, supporting GPT-3/GPT-4 chat completions, DALL-E image generation, and ChatGPT-… | 28 | 2366 | active |
| vercel/ai-elements AI Elements is a React component library and custom shadcn/ui registry from Vercel providing pre-built, composable UI components for AI-nat… | 75 | 2365 | active |
| neavo/LinguaGacha LinguaGacha is an AI-powered desktop text translator that batch-translates novels, game scripts, subtitles, and ebooks using LLM APIs (Open… | 83 | 2364 | active |
| drl990114/MarkFlowy MarkFlowy is a lightweight, cross-platform Markdown and text editor built with Tauri, React, and Prosemirror, offering WYSIWYG and source-c… | 99 | 2362 | active |
| uptrain-ai/uptrain UpTrain is an open-source Python platform for evaluating and improving LLM applications, offering 20+ preconfigured evaluation checks cover… | 23 | 2362 | active |
| bionic-gpt/bionic-gpt Bionic is an open-source, self-hosted enterprise AI platform written in Rust that provides a ChatGPT-like workspace with agentic runtime, R… | 91 | 2357 | active |
| zarazhangrui/lark-coding-agent-bridge A TypeScript bot that bridges Feishu/Lark messenger with a locally installed Claude Code or Codex CLI coding agent. It streams agent replie… | 56 | 2357 | active |
| alibaba/EasyRec EasyRec is a TensorFlow-based framework from Alibaba for building large-scale deep learning recommendation models covering matching, rankin… | 65 | 2356 | active |
| Observal/Observal Observal is a self-hosted registry and control plane for coding agent extensions such as Skills, MCP servers, and Agents, with a built-in i… | 80 | 2355 | active |
| Natively-AI-assistant/natively-cluely-ai-assistant Natively is a free, source-available desktop AI meeting assistant and interview copilot that provides real-time transcription, AI-generated… | 82 | 2354 | active |
| tavily-ai/tavily-mcp A Model Context Protocol (MCP) server that exposes Tavily's web search, page extraction, site mapping, and crawling tools to AI assistants … | 65 | 2354 | active |
| yctimlin/mcp_excalidraw An MCP server, CLI, and agent skill that gives AI coding agents a live, stateful Excalidraw canvas they can draw on, inspect via screenshot… | 64 | 2349 | active |
| vava-nessa/free-coding-models A CLI tool that tracks a large catalog of free coding LLM models across 20+ providers in real time, benchmarking their speed and stability.… | 78 | 2345 | active |
| agentuniverse-ai/agentUniverse agentUniverse is a Python-based multi-agent framework built on large language models, providing extensible components for building individu… | 70 | 2343 | active |
| heshengtao/comfyui_LLM_party A ComfyUI plugin providing a comprehensive set of nodes for building LLM agent workflows, including MCP server support, RAG/GraphRAG, TTS, … | 65 | 2343 | active |
| maitrix-org/llm-reasoners LLM Reasoners is a Python library that provides a standardized modular framework for advanced LLM reasoning, implementing algorithms like M… | 31 | 2343 | active |
| 1backend/1backend 1Backend is an AI-native microservices platform written in Go that combines a framework, proxy, and runtime for building distributed applic… | 76 | 2342 | active |
| MaxMiksa/Auto-Company Auto Company is a fully autonomous AI company simulation that runs 24/7 on your own PC, orchestrating 14 autonomous AI agents modeled after… | 66 | 2339 | active |
| jmiao24/Paper2Agent Paper2Agent is a multi-agent AI system that automatically converts research paper codebases into interactive AI agents with minimal human i… | 47 | 2338 | active |
| FrancyJGLisboa/agent-skill-creator Agent Skill Creator is a Python tool that turns human expertise (sentences, documents, scripts) into tested, installable agent skills for A… | 61 | 2335 | active |
| hydropix/TranslateBooksWithLLMs A desktop application that translates full-length books, subtitles, and documents using local or cloud LLMs (Ollama, OpenAI-compatible APIs… | 82 | 2334 | active |
| samanhappy/mcphub MCPHub is a self-hosted hub that centrally manages multiple Model Context Protocol (MCP) servers and exposes them through unified Streamabl… | 82 | 2333 | active |
| openlake-project/openlake OpenLake is a high-performance distributed storage engine written in Rust (built on io_uring, RDMA, and GPUDirect) designed to feed GPUs du… | 81 | 2330 | active |
| fruitbars/simple-one-api A single-binary Go gateway that unifies access to multiple LLM providers (Qianfan, iFlytek Spark, Tencent Hunyuan, MiniMax, DeepSeek, etc.)… | 91 | 2329 | active |
| refuel-ai/autolabel Autolabel is a Python library for labeling, cleaning, and enriching text datasets using large language models like GPT-4, Claude, and open-… | 25 | 2329 | active |
| PhialsBasement/Chain-of-Recursive-Thoughts CoRT (Chain of Recursive Thoughts) is a tool that makes LLMs recursively refine their answers by generating multiple alternative responses,… | 28 | 2328 | active |
| 1517005260/graph-rag-agent A Python framework that integrates GraphRAG, LightRAG, and Neo4j-based graph building to construct knowledge graphs and perform explainable… | 43 | 2326 | active |
| facebookresearch/schedule_free A PyTorch library implementing schedule-free optimizers (SGD, AdamW, RAdam variants) that remove the need for learning rate schedules or sp… | 67 | 2323 | active |
| PKU-YuanGroup/MoE-LLaVA MoE-LLaVA is an open-source Mixture-of-Experts based sparse large vision-language model, released with the MoE-Tuning training strategy fro… | 31 | 2322 | active |
| severian42/GraphRAG-Local-UI A local-first GraphRAG application adapted from Microsoft's GraphRAG, providing a FastAPI backend plus Gradio-based UIs for indexing, promp… | 14 | 2321 | active |
| makecindy/cindy Cindy is an open-source AI agent client (desktop and mobile apps) that unifies multiple agent harnesses like Claude Code, Codex, and Pi wit… | 80 | 2316 | active |
| trypromptly/LLMStack LLMStack is a no-code platform for building generative AI agents, workflows, and chatbots by chaining multiple LLMs and connecting them to … | 30 | 2311 | active |
| 0xMassi/webclaw webclaw is a Rust-based web extraction toolkit that turns any URL into clean, LLM-ready markdown, JSON, or token-optimized text, including … | 77 | 2305 | active |
| XiaomiMiMo/MiMo Xiaomi's MiMo is a 7B-parameter reasoning language model trained from pretraining through posttraining with reinforcement learning, release… | 30 | 2299 | active |
| togethercomputer/OpenChatKit OpenChatKit is an open-source toolkit from Together, LAION, and Ontocord.ai for building and fine-tuning chat language models, including in… | 30 | 8984 | maintenance |
| HKUDS/FastCode FastCode is a token-efficient framework for repository-scale code understanding and reasoning, using structural scouting over a semantic ma… | 58 | 2292 | active |
| huggingface/picotron Picotron is a minimalist, hackable distributed training framework for pre-training Llama-like large language models using 4D parallelism (d… | 40 | 2289 | active |
| romgX/openrelay OpenRelay is a desktop application that aggregates AI model quotas from local tools (Claude Desktop, Kiro, Windsurf, Copilot, etc.) and dir… | 76 | 2286 | active |
| sqliteai/warp WARP is a dependency-free, embeddable C inference engine that runs trillion-parameter mixture-of-experts models like Kimi K3 by streaming a… | 80 | 2284 | active |
| financial-datasets/mcp-server A Model Context Protocol (MCP) server that exposes the Financial Datasets stock market API to AI assistants like Claude Desktop. It provide… | 31 | 2282 | active |
| llmsresearch/paperbanana An open-source, community implementation of Google Research's PaperBanana paper, providing an agentic Python framework that generates publi… | 78 | 2281 | active |
| dice2o/BingGPT BingGPT is a cross-platform desktop application that provides access to new Bing's AI-powered chat without requiring Microsoft Edge or brow… | 21 | 8917 | maintenance |
| Karben233/bili-hardcore A Rust CLI tool that automatically answers Bilibili's 'hardcore member' daily quiz questions using LLM APIs. It also ships as an agent skil… | 85 | 2278 | active |
| InternLM/lagent Lagent is a lightweight Python framework for building LLM-based agents, designed with a PyTorch-like philosophy where agents are composed l… | 84 | 2278 | active |
| jamubc/gemini-mcp-tool A Model Context Protocol (MCP) server that lets AI assistants like Claude Code invoke the Google Gemini CLI (or its successor, the Antigrav… | 79 | 2278 | active |
| kevinluosl/deepbot DeepBot is a system-level AI assistant desktop application (Electron/TypeScript) that automates enterprise and personal workflows through m… | 58 | 2272 | active |
| Liuziyu77/Visual-RFT Official research code for Visual-RFT and Visual-ARFT, applying GRPO-based reinforcement fine-tuning with rule-based verifiable rewards to … | 42 | 2271 | active |
| aixcoder-plugin/aiXcoder-7B Official repository for aiXcoder-7B, an open-weights 7B-parameter code large language model trained on 1.2T tokens for code completion, gen… | 29 | 2271 | active |
| OpenDCAI/DataFlex DataFlex is a data-centric training framework built on LLaMA-Factory that dynamically schedules LLM training data during optimization. It p… | 67 | 2270 | active |
| yawiii/ComfyUI-Prompt-Assistant A ComfyUI plugin that provides an all-in-one prompt assistant, connecting to cloud LLM/VLM APIs (Zhipu, SiliconFlow, Gemini, Baidu) and loc… | 70 | 2269 | active |
| cytostack/openwolf OpenWolf is a Node.js CLI that maintains a single portable project memory (a .wolf/ directory) shared across coding agents like Claude Code… | 81 | 2268 | active |
| codedogQBY/ReadAny ReadAny is a local-first, AI-powered cross-platform e-book reader for desktop and mobile. It combines RAG-based chat with your books, hybri… | 81 | 2267 | active |
| mainframecomputer/fullmoon-ios fullmoon is a free, open-source iOS/iPadOS/macOS/visionOS app for chatting with local large language models, built on Apple's MLX Swift fra… | 33 | 2267 | active |
| lioensky/VCPToolBox VCPToolBox is a Node.js middleware layer deployed between LLM APIs and frontend applications, providing a unified Variable & Command Protoc… | 79 | 2265 | active |
| qhjqhj00/MemoRAG MemoRAG is a Python RAG framework that uses a super-long memory model to build a global understanding of an entire corpus (up to ~1M tokens… | 43 | 2265 | active |
| QwenAudio/qwen-audio-agent A realtime voice runtime and frontend for AI coding agents like Claude Code, Codex, and Qwen Code, letting agents talk, listen, and report … | 79 | 2264 | active |
| radixark/miles Miles is an open-source, enterprise-grade reinforcement learning framework for large-scale LLM and VLM post-training, forked from and co-ev… | 72 | 2263 | active |
| wusimpl/AntigravityQuotaWatcher A VS Code/Antigravity IDE extension that displays real-time AI model quota usage in the status bar. It auto-detects the Antigravity service… | 60 | 2261 | active |
| numman-ali/cc-mirror CC-MIRROR is an npm-distributed CLI that creates isolated, provider-native variants of Claude Code wired to alternative LLM providers such … | 72 | 2259 | active |
| GammaLabTechnologies/harmonist Harmonist is a portable multi-agent orchestration framework for AI coding assistants like Cursor, Claude Code, Copilot, and Windsurf, shipp… | 71 | 2258 | active |
| langfengQ/verl-agent verl-agent is an extension of the veRL framework for training LLM and VLM agents via reinforcement learning, featuring step-independent mul… | 56 | 2256 | active |
| leo-lilinxiao/codex-autoresearch A Codex skill that runs a self-directed iterative loop: it makes one focused change, measures it against a target metric, keeps improvement… | 74 | 2255 | active |
| aattaran/deepclaude A shell/PowerScript wrapper that launches Claude Code's autonomous coding agent loop backed by cheaper Anthropic-compatible LLM providers l… | 56 | 2254 | active |
| PrismML-Eng/Bonsai-demo A demo repository for running PrismML's Bonsai family of 1-bit and ternary-quantized language models locally via llama.cpp and MLX. It prov… | 59 | 2252 | active |
| dsphper/lanhu-mcp A Model Context Protocol (MCP) server that integrates the Lanhu design collaboration platform with AI coding assistants like Cursor, Claude… | 80 | 2248 | active |
| coleam00/mcp-crawl4ai-rag An MCP server that combines Crawl4AI web crawling with RAG capabilities backed by a Supabase vector database, exposing tools for AI agents … | 34 | 2245 | active |
| jwadow/kiro-gateway A self-hosted proxy API gateway for the Kiro API (Amazon Q Developer / AWS CodeWhisperer) that exposes Claude and other models through Open… | 65 | 2241 | active |
| GalTransl/GalTransl GalTransl is an automated translation tool for visual novels (galgames) that leverages large language models like GPT-4, Claude, Deepseek, … | 84 | 2239 | active |
| datapizza-labs/datapizza-ai Datapizza AI is a Python framework for building production-ready generative AI applications with agents, LLM clients, and RAG pipelines. It… | 68 | 2239 | active |
| codejunkie99/agentic-stack A Python-based framework providing a portable .agent/ folder of memory, skills, and protocols that plugs into many coding-agent harnesses (… | 79 | 2238 | active |
| Doriandarko/deepseek-engineer DeepSeek Engineer is a Python command-line coding assistant that connects to the DeepSeek API and uses function calling to read, create, an… | 32 | 2238 | active |
| IBM/AssetOpsBench AssetOpsBench is an open-source benchmark and framework from IBM for building, orchestrating, and evaluating domain-specific AI agents for … | 64 | 2237 | active |
| YFGaia/dify-plus Dify-Plus is an enterprise-enhanced fork of the Dify LLM application platform, adding a management center built on gin-vue-admin plus enter… | 75 | 2236 | active |
| apconw/Aix-DB Aix-DB is an AI-powered data analysis system (ChatBI) built on LangChain/LangGraph with an MCP Skills multi-agent architecture, converting … | 72 | 2234 | active |
| microsoft/LLaVA-Med LLaVA-Med is a large language-and-vision assistant fine-tuned for the biomedicine domain, built on the LLaVA multimodal architecture. It su… | 40 | 2231 | active |
| asuojun/claude-vision-skill A small JavaScript skill/script that gives vision-less LLM setups (like Claude Code with DeepSeek) image understanding by sending images to… | 58 | 2229 | active |
| baturyilmaz/wordpecker-app WordPecker is a personalized language-learning web application that combines Duolingo-style lessons with user-curated vocabulary lists. It … | 36 | 2229 | active |